© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93019
    Prev
    Next
    INDEX
    Explanations

    structure and leadership

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron lights up on “content‐heavy” tokens—that is, less common words (adjectives, names, key nouns, punctuation) rather than common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ♓
    -0.93
    拯救
    -0.82
     Peso
    -0.80
    endamento
    -0.75
     озе
    -0.75
    ள
    -0.75
    ♊
    -0.74
     pij
    -0.71
    今日は
    -0.71
    Mercury
    -0.70
    POSITIVE LOGITS
     fixed
    0.85
    Brave
    0.79
     asser
    0.77
    Heil
    0.76
     heat
    0.76
     sign
    0.75
     leadership
    0.75
    madamente
    0.74
     Fixed
    0.73
     Feuerwehr
    0.73
    Activations Density 0.006%

    No Known Activations